Agentic AI: From Zero to Building Autonomous Agents – Live Training

Agentic AI: From Zero to Building Autonomous Agents – Live Training

 

 

Module 1 — Foundations of Agentic AI 

What is Agentic AI?

• • Generative vs. Agentic AI
  • Workflow vs. AI agent
  • The ReAct framework, types of agents, and agentic architectures
  • Live demos of real agents

How LLMs Actually Work

• • Tokens, context windows, hallucinations — intuition, no math
  • What a prompt really is: composition of a formal prompt

Prompt Engineering for Agents

• • Zero-shot, few-shot, chain-of-thought, and ReAct prompting

APIs & Workspace Setup

• • What an API key is Getting your OpenAI/Gemini key
  • Setting up your n8n workspace — no code fear

 

Module 2 — Building Agents Without Code: n8n

n8n Fundamentals

• • Structure of an n8n workflow
  • n8n vs. Zapier vs. Make
  • Your first data pipeline: form to CRM 

Automation Pipelines

• • Automating lead generation: Google Form to CRM
  • Triggers, nodes, and data flow

Routing & Branching Logic

• • Automated social media pipeline with advanced routing and branching

AI Support Triage Agent

• • Your first AI agent: LLM + prompts + tools
  • Incoming emails classified, routed, and logged to a database

Invoice Data Extraction Agent

• • Structured outputs: forcing strict JSON schemas so AI returns clean, reliable data

Agent Tools & Memory

• • A recommendations agent with tools, memory, and real-world architecture · Why agents forget

RAG — The Concept

• • Knowledge bases, vector embeddings, chunking, semantic search — explained visually

RAG — The Build

• • Your first RAG workflow: from knowledge base to conversational AI

Telegram RAG Assistant

• • A conversational Telegram bot with advanced retrieval — a real AI assistant on your phone

Mini-Project

• • Your Personal AI Representative

 

Module 3: Just Enough Python 

Everything runs in Google Colab in the browser — no local Python installation.

Python Basics I
Variables

strings

lists

dictionaries

Python Basics II

Functions

loops

working with JSON

Your First LLM Call in Code

Calling the LLM API directly from Python — the same brain n8n used, now under the hood

Function Calling Demystified

How LLMs really use tools: manual JSON tool schemas and the function-calling mechanism

Build an Agent From Scratch I

The ReAct agent loop with the raw API — no framework, full understanding

Build an Agent From Scratch II

The ReAct prompt: building an AI agent even without function calling — the “aha” moment of the course

 

Module 4: Agent Engineering with LangChain

LangChain Essentials

Prompt templates

chat models

chains

Build a text-summarizer chain

Debugging and tracing

LangChain Agents

Your first LangChain agent with tools and LLMs

Real-world web search with Tavily

Structured outputs with Pydantic

RAG with LangChain

Document loaders

text splitters

embeddings

vector database — a complete RAG pipeline in code

Mini-Project #2 begins

MCP — Model Context Protocol

Why MCP exists and how LLMs really use tools under it

MCP architecture and servers

Using a pre-built MCP server with AI clients

Mini-Project #2 due & shared

 

Module 5: Multi-Agent Systems & Production Reality 

Multi-Agent Systems (No-Code)

A multi-agent marketing team: supervisor & worker architecture · Sequential agents and context handoff between agents

Error Handling & Self-Healing Pipelines

Centralized error handling in n8n · Building workflows that recover from failure — production-grade reliability

Agent Security & Safe AI

LLM application security · Common vulnerabilities in AI-generated apps · Guardrails and human-in-the-loop checkpoints

LLM Apps in Production & Capstone Prep

Privacy and data retention · Production architecture insights · Mapping agent patterns (ReAct, supervisor–worker, sequential handoff) to your capstone

 

Module 6 — Capstone Project

Capstone structure — participants choose their track (both equally valid):

Capstone Kickoff

Choose your track and project · Scoping & success criteria · Expect 4–6 hours of your own build time across these two weeks

Guided Build Sessions

Hands-on building with live instructor support

Polish & Rehearse

Debugging clinic, demo preparation

Demo Day

Capstone presentations · Working links shared · Certificates · Next steps